US2021092900A1PendingUtilityA1
Plant Pickers, And Related Methods Associated With Yield Detection
Est. expirySep 30, 2039(~13.2 yrs left)· nominal 20-yr term from priority
Inventors:Adrian A.W. CartierFei ChenMackenzie A. KolbetPatricio S. La Rosa ArayaE. Scott MorrisAlexander Harry SheridanVallapakrishna Sreeram
A01D 41/1272H04L 67/12G05B 19/4155A01D 45/02A01D 41/127G05B 2219/45003A01D 46/30
54
PatentIndex Score
0
Cited by
0
References
0
Claims
Abstract
Systems and methods are provided for adapting picker yield data collected by pickers (e.g., ear pickers, combines, etc.) to account for errors in calibration of the pickers. One exemplary computer-implemented method includes accessing data for a field harvested by multiple pickers, wherein the accessed data includes yield data for the field received from of the pickers, and determining a mass differential for a crop harvested by the pickers from the field. When the mass differential exceeds a threshold, the method then further includes calculating a normalization factor for at least one pair of the pickers, calculating a scaling factor associated with one of the pickers of the at least one pair of the pickers based on the normalization factor, and applying the scaling factor to the yield data received from the pickers such that the yield data is normalized.
Claims
exact text as granted — not AI-modifiedWhat is claimed is:
1 . A computer-implemented method for use in adjusting picker yield data collected by pickers to account for errors in calibration, the method comprising:
accessing data for a field harvested by at least one picker, wherein the accessed data includes yield data for the field received from the at least one picker; determining, by a computing device, a mass differential for a crop harvested by the at least one picker from the field; and in response to the mass differential exceeding a threshold:
calculating, by the computing device, a normalization factor for at least one pair of picker instances associated with the at least one picker;
calculating, by the computing device, a scaling factor associated with one of the picker instances of the at least one pair of picker instances based on the normalization factor;
applying, by the computing device, the scaling factor to the yield data received from the at least one picker, such that the yield data is normalized; and
storing, by the computing device, in a data structure, the normalized yield data.
2 . The computer-implemented method of claim 1 , wherein calculating, by the computing device, the normalization factor includes calculating a normalization factor for each pair of the picker instances having at least a threshold number of neighboring data points within the accessed data, wherein the neighboring data points include data points for adjacent swaths in the field; and
wherein the method further comprises:
omitting a normalization factor for a pair of the picker instances, for data points of the picker instances in adjacent swaths formed by the at least one picker in the field, when said pair of the picker instances includes less than the threshold number of neighboring data points within the accessed data; and
calculating, by the computing device, a normalization factor for said pair of the picker instances that include less than the threshold number of neighboring data points within the accessed data based on an intermediary picker instance having at least a threshold number of neighboring data points within the accessed data with each of said pair of the picker instances.
3 . The computer-implemented method of claim 2 , wherein calculating a normalization factor for said pair of the picker instances that include less than the threshold number of neighboring data points within the accessed data includes:
calculating, by the computing device, a first intermediate normalization factor for a first one of said pair of the picker instances and the intermediary picker instance; calculating, by the computing device, a second intermediate normalization factor for a second one of said pair of the picker instances and the intermediary picker instance; and combining the first and second intermediate normalization factors to produce the normalization factor for said pair of the picker instances that include less than the threshold number of neighboring data points within the accessed data; and wherein determining the mass differential for the crop includes calculating the mass differential as the yield mass based on accessed yield data less a weighed mass, divided by the weighed mass.
4 . The computer-implemented method of claim 1 , wherein calculating the scaling factor associated with one of the picker instances includes calculating the scaling factor based on the following algorithm:
s
f
i
=
truckload
∑
j
=
1
n
∑
x
,
y
n
f
ij
Y
j
(
x
,
y
)
A
j
(
x
,
y
)
;
wherein sf i is the scaling factor for the one of the picker instances of the at least one pair of the picker instances, the truckload is the weight of the crop harvested from the field by the one of the picker instances of the at least one pair of the picker instances, nf ij is the normalization factor for the at least one pair of the picker instances, Y j (x,y) is a yield data point in mass of the crop yield per unit area collected by the other one of the picker instances of the at least one pair of the picker instances at the location (x,y), and A j (x,y) is an area associated with the yield data point Y j (x,y).
5 . The computer-implemented method of claim 1 , wherein applying the scaling factor includes applying the scaling factor consistent with at least one of the following algorithms, thereby providing the normalized yield data:
norm_yld j =( nf ij ×sf i ) Ŷ j ( x, y ); and norm_yld i =( sf i ) Ŷ i ( x, y ); wherein norm_yld i is the normalized yield data at location (x, y) for the picker instance i of the at least one pair of the picker instances, norm_yld j is the normalized yield data at location (x,y) for the other one of the picker instances, j, of the at least one pair of the picker instances, nf ij is the normalization factor for the at least one pair of the picker instances, sf i is the scaling factor for the one of the picker instances of the at least one pair of the picker instances, Ŷ j (x,y) is the calculated yield for the other one of the picker instances of the at last one pair of picker instances at the location (x,y), and Ŷ i (x,y) is the calculated yield for the one of the picker instances of the at last one pair of the picker instances at the location (x,y).
6 . The computer-implemented method of claim 1 , further comprising compiling, by the computing device, a yield map for the field, based on the normalized yield data; and
wherein the at least one picker includes at least one of a corn ear picker and a combine harvester.
7 . The computer-implemented method of claim 1 , further comprising receiving, by the computing device, from at least one of the picker instances, the data for the field, the data including at least one or more of an electrical signal indicative of an amount of the crop harvested by the at least one of the picker instances and/or a calculated yield for the at least one of the picker instances based on a conversion factor associated with said at least one of the picker instances.
8 . The computer-implemented method of claim 1 , wherein the at least one picker includes multiple pickers, and wherein each of the picker instances is associated with one of the multiple pickers; and
wherein the method further comprises compiling a matrix of multiple normalization factors for the multiple pickers.
9 . The computer-implemented method of claim 8 , further comprising calculating one of the multiple normalization factors for a pair of the multiple pickers through an intermediary picker from the multiple pickers, based on the following:
n
f
i
j
=
K
i
K
j
=
K
i
K
k
K
k
K
j
=
n
f
i
k
n
f
k
j
.
10 . The computer-implemented method of claim 1 , wherein multiple ones of the picker instances are associated with a same one of the at least one picker; and/or
wherein the at least one picker includes a first picker and a second picker, and wherein multiple ones of the picker instances are associated with the first picker and the second picker.
11 . The computer-implemented method of claim 1 , wherein the accessed data includes yield data for only a portion of the field; and
wherein the method further comprises, prior to determining the mass differential for the crop, approximating yield data for the field based on a distribution of the yield data for the portion of the field.
12 . A system for adjusting yield data collected by pickers to account for errors in calibration of the pickers, the system comprising:
a data structure including yield data for a field harvested by multiple pickers, the yield data including actual yield data determined based on a weight of a crop harvested by the pickers from the field and calculated yield data based on conversion factors associated with each of the pickers; and a field engine computing device in communication with the data structure, the field engine computing device configured to:
calculate a mass differential for a crop harvested by the pickers from the field based on the actual yield data and the calculated yield data in the data structure;
determine that the mass differential exceeds a threshold; and
in response to the determination that the mass differential exceeds the threshold:
calculate a normalization factor for at least one pair of the pickers;
calculate a scaling factor associated with one of the pickers of the at least one pair of the pickers based on the normalization factor;
apply the scaling factor to the calculated yield data for each of the pickers of the at least one pair of the pickers, such that the calculated yield data is normalized; and
store the normalized yield data for each of the pickers of the at least one pair of the pickers in the data structure.
13 . The system of claim 12 , wherein the field engine computing device is configured, in connection with calculating the normalization factor, to calculate a normalization factor for each pair of the pickers having at least a threshold number of neighboring data points within the accessed data, and wherein the neighboring data points include data points for adjacent swaths in the field.
14 . The system of claim 12 , wherein the field engine computing device is further configured, in connection with calculating the scaling factor associated with one of the pickers of the at least one pair of the pickers, to calculate the scaling factor based on the following algorithm:
s
f
i
=
truckload
∑
j
=
1
n
∑
x
,
y
n
f
ij
Y
j
(
x
,
y
)
A
j
(
x
,
y
)
;
wherein sf i is the scaling factor for the one of the pickers of the at least one pair of the pickers, the truckload is the weight of the crop harvested from the field by the one of the pickers of the at least one pair of the pickers, nf ij is the normalization factor for the at least one pair of the pickers, Y j (x,y) is a yield data point in mass of the crop yield per unit area collected by the other one of the pickers of the at least one pair of pickers at the location (x,y), and A j (x,y) is an area associated with the yield data point Y j (x,y).
15 . The system of claim 12 , wherein the field engine computing device is further configured, in connection with applying the scaling factor, to apply the scaling factor consistent with at least one of the following algorithms, thereby providing the normalized yield data:
norm_yld j =( nf ij ×sf i ) Ŷ j ( x, y ); and norm_yld i =( sf i ) Ŷ i ( x, y ); wherein norm_yld i is the normalized yield data at location (x, y) for the picker i of the at least one pair of the pickers, norm_yld j is the normalized yield data at location (x, y) for the other one of the pickers, j, of the at least one pair of the pickers, nf ij is the normalization factor for the at least one pair of the pickers, sf i is the scaling factor for the one of the pickers of the at least one pair of the pickers, Ŷ j (x,y) is the calculated yield for the other one of the pickers of the at last one pair of pickers at the location (x,y), and Ŷ i (x,y) is the calculated yield for the one of the pickers of the at last one pair of pickers at the location (x,y).
16 . The system of claim 12 , further comprising the pickers;
wherein each of the pickers is configured to transmit data for the crop harvested from field to the field engine computing device; wherein the data transmitted by each of the pickers to the field engine computing device includes at least one or more of an electrical signal indicative of an amount of the crop harvested by the picker and/or the calculated yield for the picker based on the conversion factor associated with said picker; and wherein each of the pickers includes a corn ear picker or a combine harvester.
17 . A non-transitory computer readable storage medium including executable instructions for adjusting yield data collected by harvesting machines to account for errors in calibration of the harvesting machines, which when executed by at least one processor, cause the at least one processor to:
access data for a field harvested by at least one harvesting machine, wherein the accessed data includes actual yield data for the at least one harvesting machine determined based on a weight of a crop harvested by the at least one harvesting machine from the field and calculated yield data based on a conversion factor associated with each instance associated with the at least one harvesting machine; calculate a mass differential for a crop harvested by each instance associated with the at least one harvesting machine from the field based on the actual yield data and the calculated yield data; determine whether the mass differential exceeds a threshold; and in response to the mass differential exceeding the threshold:
calculate a normalization factor for at least one pair of instances associated with the at least one harvesting machine;
calculate a scaling factor associated with one of the instances of the at least one pair of the instances based on the normalization factor;
apply the scaling factor to the calculated yield data for each of the instances of the at least one pair of the instances, such that the calculated yield data is normalized; and
store the normalized yield data for each of the instances of the at least one pair of the instances in a data structure.
18 . The non-transitory computer readable storage medium of claim 17 , wherein the executable instructions, when executed by the at least one processor in connection with calculating the scaling factor associated with one of the instances of the at least one pair of the instances, cause the at least one processor to calculate the scaling factor based on the following algorithm:
s
f
i
=
truckload
∑
j
=
1
n
∑
x
,
y
n
f
ij
Y
j
(
x
,
y
)
A
j
(
x
,
y
)
;
wherein sf i is the scaling factor for the one of the instances of the at least one pair of the instances, the truckload is the weight of the crop harvested from the field by the one of the instances of the at least one pair of the instances, nf ij is the normalization factor for the at least one pair of the instances, Y j (x,y) is a yield data point in mass of the crop yield per unit area collected by the other one of the instances of the at least one pair of instances at the location (x,y), and A j (x,y) is an area associated with the yield data point Y j (x,y).
19 . The non-transitory computer readable storage medium of claim 17 , wherein the executable instructions, when executed by the at least one processor in connection with applying the scaling factor, further cause the at least one processor to apply the scaling factor consistent with at least one of the following algorithms, thereby providing the normalized yield data:
norm_yld j =( nf ij ×sf i ) Ŷ j ( x, y ); and norm_yld i =( sf i ) Ŷ i ( x, y ); wherein norm_yld i is the normalized yield data at location (x, y) for the instance i of the at least one pair of the instances, norm_yld j is the normalized yield data at location (x, y) for the other one of the instances, j, of the at least one pair of the instances, nf ij is the normalization factor for the at least one pair of the instances, sf i is the scaling factor for the one of the instances of the at least one pair of the instances, Ŷ j (x,y) is the calculated yield for the other one of the instances of the at last one pair of instances at the location (x,y), and Ŷ i (x,y) is the calculated yield for the one of the instances of the at last one pair of instances at the location (x,y).
20 . The non-transitory computer readable storage medium of claim 17 , wherein the at least one harvesting machine includes at least one of a corn ear picker and a combine harvester; and
wherein:
the at least one harvesting machine includes multiple harvesting machines, and each of the instances includes one of the multiple harvesting machines; and/or
multiple ones of the instances are associated with a same one of the at least one harvesting machine.Join the waitlist — get patent alerts
Track US2021092900A1 — get alerts on status changes and closely related new filings.
We store only your email — no account needed. See our privacy policy.